Arnold Chen's repositories
efficientdet
(Pretrained weights provided) EfficientDet: Scalable and Efficient Object Detection implementation by Signatrix GmbH
Activity-Recognition-TensorRT
3D ResNet Video Classification accelerated by TensorRT
data-preprocessing
Scripts for data preprocessing and dataset construction
Yet-Another-EfficientDet-Pytorch
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
CaridDetect-OpenCV
CaridDetect OpenCV version
coco2yolo
Converts MS COCO to YOLO,given data foramt to COCO and DOTA to COCO
DBFace
DBFace is a real-time, single-stage detector for face detection, with faster speed and higher accuracy
deep_sort
Simple Online Realtime Tracking with a Deep Association Metric
depth_clustering
:taxi: Fast and robust clustering of point clouds generated with a Velodyne sensor.
fast-reid
SOTA ReID Methods and Toolbox
gstreamer
GStreamer open-source multimedia framework
hard_decode_trt
Yolov5 inference on NVDec hardware decoder
ICCVW21-LiDAR-Panoptic-Segmentation-TradiCV-Survey-of-Point-Cloud-Cluster
A hybrid SOTA solution of LiDAR panoptic segmentation with C++ implementations of point cloud clustering algorithms. ICCV21, Workshop on Traditional Computer Vision in the Age of Deep Learning
imgtools-opencv-code
util code for processing/diff images basing on opencv
kitti2bag
Convert KITTI dataset to ROS bag file the easy way!
mediapipe
Cross-platform, customizable ML solutions for live and streaming media.
pcd2rosbag
convert pcd files to rosbag
rosbridge2cpp
A C++11 library to interface ROS via rosbridge
second.pytorch
SECOND for KITTI/NuScenes object detection
shouxie_RNN
shouxie_RNN
STDC-Seg
Source Code of our CVPR2021 paper "Rethinking BiSeNet For Real-time Semantic Segmentation"
tensorflow-onnx
Convert TensorFlow models to ONNX
TensorRT
TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.
tensorRTIntegrate
TensorRT ONNX Plugin、Inference、Compile
tflite_gles_app
GPU accelerated deep learning inference applications for RaspberryPi / JetsonNano / Linux PC using TensorflowLite GPUDelegate / TensorRT
Yolo-Fastest
:zap: Yolo universal target detection model combined with EfficientNet-lite, the calculation amount is only 230Mflops(0.23Bflops), and the model size is 1.3MB
yolov5_trt
Implement yolov5 s/m//l/x with TensorRT API and support serialization/deserialization+image detection/video detection and recording